quantization_metadata.json

{
  "model_name": "qingy2024/Qwen3-VLTO-32B-Instruct",
  "quantization_format": "NVFP4",
  "calibration_samples": 1024,
  "original_memory_gb": "65.52",
  "quantized_memory_gb": "65.53",
  "memory_reduction_percent": "-0.0",
  "total_parameters_billions": "32.76",
  "target_device": "DGX Spark (GB10)",
  "export_path": "/workspace/quantized-output/Qwen3-VLTO-32B-Instruct-NVFP4-256K",
  "quantization_config": {
    "model_name": "qingy2024/Qwen3-VLTO-32B-Instruct",
    "quantization_format": "NVFP4",
    "calibration_samples": 1024,
    "calibration_max_length": 2048,
    "calibration_min_length": 100,
    "calibration_dataset": "allenai/c4",
    "calibration_dataset_config": "en",
    "calibration_dataset_split": "train",
    "target_device": "DGX Spark (GB10)",
    "hf_cache_dir": "~/.cache/huggingface",
    "output_dir": "./quantized-output/Qwen3-VLTO-32B-Instruct-NVFP4-256K",
    "log_dir": "./logs",
    "torch_dtype": "bfloat16",
    "device_map": "auto",
    "trust_remote_code": true
  },
  "created_at": "2025-11-04T02:20:20.853500"
}